© 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. 64099
    Prev
    Next
    INDEX
    Explanations

    code increment and assignment

    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
     selam
    -0.94
    Obstacles
    -0.91
    Additions
    -0.90
    Demographics
    -0.90
     leto
    -0.88
    Ouv
    -0.88
    anın
    -0.87
    埒
    -0.87
     sobot
    -0.85
     Begins
    -0.84
    POSITIVE LOGITS
    ++;
    1.06
     });
    1.05
    moveToNext
    0.99
    ++;
    0.94
    Thirty
    0.93
    ()));
    0.91
     advances
    0.90
    MoveNext
    0.89
    ();
    0.89
     move
    0.86
    Activations Density 0.005%

    No Known Activations