© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67036
    Prev
    Next
    INDEX
    Explanations

    opened, chaired, reprise, winner

    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
    }$.
    -1.55
    。
    -1.53
     даже
    -1.53
    —
    -1.50
    €”
    -1.49
     kahit
    -1.48
    ;—
    -1.38
     bahkan
    -1.38
    --
    -1.37
    んだから
    -1.35
    POSITIVE LOGITS
     from
    2.13
    ス
    1.59
     regarding
    1.51
    軀
    1.44
     representar
    1.38
    อีก
    1.37
    ,
    1.37
     разом
    1.36
     วาด
    1.34
    จาก
    1.34
    Activations Density 0.427%

    No Known Activations