© 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. 31-GEMMASCOPE-2-RES-65K
    7. 61952
    Prev
    Next
    INDEX
    Explanations

    the key is

    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_31_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
     denunci
    0.43
     entrambi
    0.43
    振
    0.42
    西
    0.40
    混合
    0.40
     đông
    0.40
    initis
    0.39
     descenso
    0.39
     entrar
    0.38
     imediatamente
    0.38
    POSITIVE LOGITS
     Preserve
    0.43
     QC
    0.43
     Source
    0.40
     Preservation
    0.40
     amount
    0.39
    wq
    0.39
    ":"",
    0.38
    positions
    0.38
     збере
    0.38
     Amount
    0.38
    Activations Density 0.004%

    No Known Activations