© 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. 64171
    Prev
    Next
    INDEX
    Explanations

    game changer breaker stopper

    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
    焗
    -0.78
     voeten
    -0.75
     landlord
    -0.72
     Botan
    -0.71
     coordinating
    -0.69
    ichel
    -0.66
     some
    -0.66
    ciutto
    -0.66
     pap
    -0.65
    harry
    -0.65
    POSITIVE LOGITS
     changer
    1.27
     breaker
    1.20
    breaker
    1.13
    stopper
    1.07
     stopper
    1.02
     killers
    0.97
     Breaker
    0.96
    changer
    0.94
     Changer
    0.93
     breakers
    0.90
    Activations Density 0.021%

    No Known Activations