© 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. 138269
    Prev
    Next
    INDEX
    Explanations

    files recovery

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

    comparing models (Gemma, GPT4All, Bard)

    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
     остальные
    0.50
     її
    0.49
     её
    0.48
     ее
    0.47
    内の
    0.46
     Ú
    0.46
    気の
    0.46
    !")
    0.45
    <0x86>
    0.45
    その他の
    0.45
    POSITIVE LOGITS
     militias
    0.47
    Stephen
    0.45
     sermons
    0.44
     riffs
    0.43
    atives
    0.43
     shouldUse
    0.43
    借鉴
    0.42
     marca
    0.41
     depicts
    0.41
     calendars
    0.41
    Activations Density 0.001%

    No Known Activations