© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119269
    Prev
    Next
    INDEX
    Explanations

    password protection and requirements

    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
     puisque
    -0.91
     puisqu
    -0.88
    ⡯
    -0.79
     accordo
    -0.79
    所以我
    -0.77
     Spiro
    -0.75
    transQ
    -0.74
     diesen
    -0.74
    umin
    -0.73
     bessere
    -0.73
    POSITIVE LOGITS
     reset
    1.13
     strength
    1.12
     protect
    1.07
     *****
    1.03
     complexity
    1.02
    strength
    0.99
    reset
    0.98
    hash
    0.96
     recovery
    0.93
     dimentic
    0.92
    Activations Density 0.025%

    No Known Activations