© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103711
    Prev
    Next
    INDEX
    Explanations

    retention

    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
    }
    -2.58
    of
    -2.50
    もある
    -2.20
     späteren
    -2.20
    M
    -2.19
    同じ
    -2.16
    S
    -2.11
    on
    -2.08
     richtigen
    -2.05
     Somebody
    -2.05
    POSITIVE LOGITS
    ]));
    2.25
    蠖
    2.19
    they
    2.17
    rozco
    2.17
    睺
    2.11
    ский
    2.11
    fromUtf
    2.08
     ridd
    2.06
    rie
    2.03
    俣
    2.03
    Activations Density 0.003%

    No Known Activations