© 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. 195041
    Prev
    Next
    INDEX
    Explanations

    post followed by a word or date

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

    structured lists and references

    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
    乏
    0.46
    rophiles
    0.46
    riting
    0.46
    èr
    0.44
     பெண்கள்
    0.43
    刧
    0.43
    背
    0.43
     housewives
    0.42
    詈
    0.41
    ctors
    0.40
    POSITIVE LOGITS
     toprak
    0.52
    ];
    0.48
    Muc
    0.47
     mau
    0.46
    Discrimin
    0.46
    parsed
    0.46
    dude
    0.45
     טוב
    0.45
    Dude
    0.44
    ]{
    0.44
    Activations Density 0.001%

    No Known Activations