© 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. 10-GEMMASCOPE-RES-131K
    7. 21757
    Prev
    Next
    INDEX
    Explanations

    not achieving or preventing

    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_10/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
    ￭
    -1.15
     nî
    -1.11
    目光
    -1.09
     Públicas
    -1.09
    ariously
    -1.08
     kleuren
    -1.06
     パイ
    -1.05
     gezicht
    -1.05
    ICHE
    -1.04
    делки
    -1.04
    POSITIVE LOGITS
    0
    1.20
    他们的
    1.18
    躂
    1.16
     doesn
    1.12
     dont
    1.09
     minOccurs
    1.05
    Skal
    1.05
    中です
    1.05
    他們的
    1.05
    拋
    1.05
    Activations Density 0.078%

    No Known Activations