© 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. 120698
    Prev
    Next
    INDEX
    Explanations

    mil payday

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

    AI model descriptions and stories

    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
     tantôt
    0.53
    ЭС
    0.51
     bygone
    0.46
     hypertrophy
    0.44
     graces
    0.44
    рақ
    0.44
    f
    0.44
    𝓜
    0.44
     douze
    0.43
     downgraded
    0.43
    POSITIVE LOGITS
    贸
    0.53
    螅
    0.44
     Continue
    0.44
    的影响
    0.43
     Similarly
    0.43
     Progression
    0.42
    貿
    0.42
    椇
    0.42
    敚
    0.42
     পরই
    0.41
    Activations Density 0.001%

    No Known Activations