© 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. 154190
    Prev
    Next
    INDEX
    Explanations

    listed firms

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

    mathematical and descriptive terms

    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
    脂
    0.52
    )」
    0.49
    ătă
    0.45
    मस
    0.45
    okan
    0.45
    okal
    0.45
    Após
    0.45
     वापर
    0.44
    鍱
    0.44
    需
    0.43
    POSITIVE LOGITS
     شہر
    0.52
    and
    0.48
     hound
    0.47
     country
    0.47
     chronicle
    0.45
     міста
    0.44
     Chronicle
    0.43
     strains
    0.43
     highland
    0.43
     conceal
    0.42
    Activations Density 0.000%

    No Known Activations