© 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-65K
    7. 51954
    Prev
    Next
    INDEX
    Explanations

    towards warmer, escape negativity, regularly

    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_65k_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
     prism
    0.38
    告訴
    0.37
    entz
    0.36
     dement
    0.36
    וריה
    0.36
     Juven
    0.36
     +
    0.36
     Ots
    0.36
    στ
    0.35
     столб
    0.35
    POSITIVE LOGITS
    anhyd
    0.40
    üğ
    0.39
    氷
    0.39
     createjs
    0.39
     freeze
    0.38
     },{
    0.38
     یخ
    0.38
    രിച്ചത്
    0.38
    subs
    0.38
     }</
    0.38
    Activations Density 0.002%

    No Known Activations