© 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. 208486
    Prev
    Next
    INDEX
    Explanations

    ordering requests and descriptions

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

    criteria, Northern, ejaculation, Boot

    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
     vrat
    0.58
     IRE
    0.54
     ANIM
    0.52
     スマート
    0.52
     ハイ
    0.52
     ZX
    0.51
     înv
    0.50
    ד
    0.50
    IRE
    0.49
    <unused584>
    0.49
    POSITIVE LOGITS
    ietta
    0.43
    olok
    0.43
    fabric
    0.42
    lo
    0.41
    "
    0.41
    ol
    0.41
    ometries
    0.41
    arbeiten
    0.41
    瞒
    0.41
    锦
    0.40
    Activations Density 0.000%

    No Known Activations