© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93882
    Prev
    Next
    INDEX
    Explanations

    . object access

    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
     ]);
    -1.08
     innumerable
    -1.03
     ];
    -1.02
     يقول
    -0.93
    іе
    -0.91
     Says
    -0.90
    ığınız
    -0.89
    }">
    -0.88
     dunque
    -0.88
    foglal
    -0.86
    POSITIVE LOGITS
     assumes
    1.73
     also
    1.55
    Dabei
    1.40
     Dabei
    1.36
     assumed
    1.30
     returns
    1.26
     will
    1.22
     intended
    1.16
     doesn
    1.14
     if
    1.10
    Activations Density 0.062%

    No Known Activations