© 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. 45225
    Prev
    Next
    INDEX
    Explanations

    undesirable states or qualities

    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
    ビーフ
    -0.81
    ツヤ
    -0.79
    igli
    -0.76
     heuristic
    -0.76
     silencing
    -0.75
    Mv
    -0.75
     metrics
    -0.75
     picante
    -0.75
    ברים
    -0.74
     corrosive
    -0.74
    POSITIVE LOGITS
     orange
    1.03
     unsightly
    0.96
     unwanted
    0.88
     bulky
    0.88
     frizz
    0.85
    umpy
    0.83
     pill
    0.81
     weird
    0.81
    orange
    0.80
     undesirable
    0.80
    Activations Density 0.030%

    No Known Activations