© 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. 33288
    Prev
    Next
    INDEX
    Explanations

    legal entities and outcomes

    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
    :
    -1.58
     any
    -1.43
     with
    -1.35
     When
    -1.29
     different
    -1.20
     various
    -1.17
    When
    -1.15
     when
    -1.13
     several
    -1.13
     more
    -1.12
    POSITIVE LOGITS
     hivyo
    1.13
     Atención
    1.09
     bluse
    1.09
     tohto
    1.09
     cincin
    1.08
     vêtement
    1.05
     imprimer
    1.05
     gouttes
    1.05
     aumentando
    1.04
     zeg
    1.03
    Activations Density 0.170%

    No Known Activations