© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78484
    Prev
    Next
    INDEX
    Explanations

    beginning of sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ఱ
    -2.08
    瘆
    -2.00
     teater
    -1.99
     plis
    -1.98
     eene
    -1.98
     fii
    -1.97
    ...»
    -1.97
     laboratorium
    -1.96
    饜
    -1.95
     dezelve
    -1.95
    POSITIVE LOGITS
     It
    4.28
     This
    3.61
     However
    3.53
     There
    3.36
     If
    3.08
     Since
    3.03
     The
    3.02
     While
    3.00
     Although
    2.98
     That
    2.92
    Activations Density 1.238%

    No Known Activations