© 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. 57233
    Prev
    Next
    INDEX
    Explanations

    html and xml attributes

    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
     Tenggara
    -1.17
     auraient
    -1.16
     désol
    -1.14
     effray
    -1.14
    Rather
    -1.12
    Either
    -1.12
     pourraient
    -1.12
     étr
    -1.11
     puissent
    -1.11
    Moreover
    -1.10
    POSITIVE LOGITS
     class
    1.55
     style
    1.37
     like
    1.25
     id
    1.18
     and
    1.13
     on
    1.12
     role
    1.10
    .)
    1.02
    ...>
    0.99
     or
    0.96
    Activations Density 0.047%

    No Known Activations