© 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. 22-GEMMASCOPE-RES-131K
    7. 65429
    Prev
    Next
    INDEX
    Explanations

    describing content types

    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_22/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
     like
    -1.16
    久し
    -1.13
    うわ
    -1.09
    валі
    -1.06
     signifikan
    -1.05
    девушка
    -1.04
     музея
    -1.04
     bestimmten
    -1.01
    𝒉
    -1.00
    -1.00
    POSITIVE LOGITS
     and
    1.51
     answers
    1.23
     analysis
    1.19
     assessment
    1.09
     answer
    1.08
     Beamten
    1.06
    <bos>
    1.05
     explanation
    0.99
     article
    0.98
    Гц
    0.98
    Activations Density 0.071%

    No Known Activations