© 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. 152495
    Prev
    Next
    INDEX
    Explanations

    avoidance syndrome

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

    material details or specific qualities

    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
    籁
    0.48
    গতের
    0.45
     Мол
    0.44
    岃
    0.44
    CreateWall
    0.44
    镂
    0.44
    র্তি
    0.43
    മിതി
    0.42
    দৃশ্য
    0.42
    衵
    0.41
    POSITIVE LOGITS
     at
    0.50
     prejud
    0.50
     impuls
    0.49
     react
    0.46
     idealism
    0.46
     optimale
    0.45
    яр
    0.45
     rapides
    0.45
     dansk
    0.45
     /ˈ
    0.44
    Activations Density 0.001%

    No Known Activations