© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 189096
    Prev
    Next
    INDEX
    Explanations

    place names or specific items

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

    dealing with consequences and resilience

    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
    łat
    0.52
    avaş
    0.52
    adım
    0.51
     만
    0.47
     접근
    0.45
     ቀላል
    0.44
    ziała
    0.44
    łach
    0.44
     engages
    0.43
    WriteStream
    0.43
    POSITIVE LOGITS
     Ordnance
    0.50
    靈
    0.50
     dank
    0.47
     Hawks
    0.46
    س
    0.46
     Speaker
    0.45
    忐
    0.45
    }}-
    0.45
    tig
    0.44
     Hawkes
    0.44
    Activations Density 0.001%

    No Known Activations