© 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. 119057
    Prev
    Next
    INDEX
    Explanations

    apiPageType enum pageType

    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
     there
    -1.64
     while
    -1.30
     their
    -1.30
     such
    -1.29
     what
    -1.28
     amidst
    -1.27
     for
    -1.25
     as
    -1.24
     with
    -1.22
     at
    -1.20
    POSITIVE LOGITS
     และ
    1.23
    癭
    1.22
     flamboyant
    1.17
    nearly
    1.16
     accentu
    1.14
     strikingly
    1.12
    cannot
    1.12
     VERY
    1.10
     deliciously
    1.09
    ishment
    1.08
    Activations Density 0.219%

    No Known Activations