© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49314
    Prev
    Next
    INDEX
    Explanations

    date and updates

    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
     when
    -2.06
     because
    -1.84
     by
    -1.76
     at
    -1.60
     before
    -1.55
     as
    -1.53
     from
    -1.48
     When
    -1.48
     for
    -1.42
     with
    -1.40
    POSITIVE LOGITS
     zoude
    1.42
    €“
    1.38
    €”
    1.36
     nabi
    1.33
     urat
    1.30
     constater
    1.30
     branco
    1.30
     kado
    1.27
    whose
    1.26
     　　
    1.26
    Activations Density 0.000%

    No Known Activations