© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 131309
    Prev
    Next
    INDEX
    Explanations

    greeting, status, enterprise, from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mapp
    0.40
    ={()
    0.40
    \|^{
    0.39
    قیه
    0.38
    ல்லாம்
    0.38
    ^{
    0.36
    னம்
    0.36
    ={{
    0.35
     storyboard
    0.35
     local
    0.34
    POSITIVE LOGITS
     esigen
    0.44
    Poss
    0.42
    aspid
    0.41
     തിരഞ്ഞെടു
    0.40
     এরূপ
    0.40
     exclusivity
    0.40
     chiếm
    0.39
    utzer
    0.38
     আকাঙ্
    0.38
    Qnt
    0.38
    Activations Density 0.000%

    No Known Activations