© 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. 77129
    Prev
    Next
    INDEX
    Explanations

    derived from

    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
    ஂ
    -1.31
    豋
    -1.20
    or
    -1.19
    柺
    -1.04
    瓩
    -1.00
    dal
    -0.98
    </code>
    -0.97
    </h1>
    -0.97
     burdened
    -0.95
    ઁ
    -0.94
    POSITIVE LOGITS
     derive
    1.53
    derive
    1.52
     Derived
    1.48
     derives
    1.45
     from
    1.44
     Deriv
    1.39
     derived
    1.38
     deriv
    1.30
     Дер
    1.22
    Derived
    1.19
    Activations Density 0.028%

    No Known Activations