© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 179641
    Prev
    Next
    INDEX
    Explanations

    replacements, replacements, replace, replace, replace, replacing, replaced, replacement

    np_acts-logits-general · gemini-2.5-flash-lite

    substitutions and exchanges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    मस्कार
    0.46
    鹖
    0.45
     nedeniyle
    0.45
    广西
    0.45
     betont
    0.44
    ликт
    0.44
     nawet
    0.44
     aufgrund
    0.44
     ausreiche
    0.44
     vorg
    0.43
    POSITIVE LOGITS
     replacements
    0.49
    replace
    0.49
     replace
    0.48
    s
    0.46
     replacing
    0.44
     substitutions
    0.43
     replaced
    0.42
     replacement
    0.42
     oh
    0.42
     BP
    0.42
    Activations Density 0.001%

    No Known Activations