© 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. 107389
    Prev
    Next
    INDEX
    Explanations

    several separate

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

    misconceptions, interruptions, flow, visuals

    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
    IEEE
    0.44
     astro
    0.44
     vyh
    0.43
     prog
    0.43
     kain
    0.43
     überw
    0.43
    㜖
    0.42
     IMF
    0.42
     philanthropy
    0.42
     電
    0.41
    POSITIVE LOGITS
    РС
    0.46
    极致
    0.45
    始终
    0.45
    ParameterActive
    0.44
    具备
    0.44
    いつでも
    0.44
    毎回
    0.44
    ដល់
    0.44
    谒
    0.43
    ڈا
    0.43
    Activations Density 0.002%

    No Known Activations