© 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. 59327
    Prev
    Next
    INDEX
    Explanations

    not describing a state

    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
    大好きな
    -0.88
    utados
    -0.83
     freund
    -0.82
    owie
    -0.82
    ائمة
    -0.77
    AHULUAN
    -0.76
    infrared
    -0.76
    −/−
    -0.75
     ZU
    -0.75
     induces
    -0.75
    POSITIVE LOGITS
     religious
    1.08
     athletic
    1.01
     patience
    0.99
     morning
    0.97
     particularly
    0.96
     easily
    0.89
     اهل
    0.89
     sporty
    0.88
    vierno
    0.85
     confrontation
    0.85
    Activations Density 0.039%

    No Known Activations