© 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. 10-GEMMASCOPE-RES-131K
    7. 104203
    Prev
    Next
    INDEX
    Explanations

    spatial locations and directions

    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
    cetta
    -1.53
    öfe
    -1.52
    }
    -1.48
    </h2>
    -1.45
    antaranya
    -1.44
    _{
    -1.40
    ništvo
    -1.34
    象徴
    -1.34
    ]."
    -1.34
    はその
    -1.33
    POSITIVE LOGITS
     when
    2.03
    Schule
    1.74
     because
    1.59
    錞
    1.38
     even
    1.38
    Gemeinde
    1.38
    뻗
    1.38
     or
    1.34
    t
    1.33
    蛧
    1.33
    Activations Density 0.022%

    No Known Activations