© 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. 162397
    Prev
    Next
    INDEX
    Explanations

    talk about, talk to, talk of

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

    talk his way

    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
    ת
    0.54
     tentang
    0.52
     về
    0.48
     población
    0.45
     saludable
    0.45
     disbursed
    0.44
    াটো
    0.44
     flavorful
    0.44
     biología
    0.43
    ة
    0.43
    POSITIVE LOGITS
     talk
    0.48
    emon
    0.47
     Talk
    0.45
    eg
    0.45
    talk
    0.44
    iy
    0.42
     ie
    0.42
     Fuchs
    0.41
     پیروی
    0.41
     Sherwood
    0.40
    Activations Density 0.014%

    No Known Activations