© 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. 172605
    Prev
    Next
    INDEX
    Explanations

    what comes after if

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

    how method within

    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
    قتها
    0.45
     comentario
    0.42
     instit
    0.41
     เห
    0.41
     lecteurs
    0.41
     peuple
    0.41
     fenomeni
    0.40
    苒
    0.40
     ਇ
    0.39
     στι
    0.39
    POSITIVE LOGITS
    dro
    0.44
     Allocated
    0.43
     schist
    0.42
    TAM
    0.41
    --’
    0.41
    lük
    0.41
     TAD
    0.41
    ços
    0.41
    amen
    0.40
    nodo
    0.40
    Activations Density 0.001%

    No Known Activations