© 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. 63334
    Prev
    Next
    INDEX
    Explanations

    use of

    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
    鸾
    -1.00
    rions
    -0.98
    ναι
    -0.97
    🤠
    -0.97
    ſſen
    -0.95
    ,:)
    -0.95
     نحوه
    -0.94
    </s>
    -0.94
    zzzz
    -0.93
    umers
    -0.93
    POSITIVE LOGITS
     technology
    2.09
     various
    1.66
     technologies
    1.64
     different
    1.59
     these
    1.53
     computers
    1.48
     such
    1.38
     our
    1.38
     multiple
    1.36
     varied
    1.35
    Activations Density 0.173%

    No Known Activations