© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 14619
    Prev
    Next
    INDEX
    Explanations

    setting up definitions or categories

    np_acts-logits-general · gemini-2.5-flash-lite

    context and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    coding
    0.47
     egress
    0.46
    inc
    0.45
    ```
    0.44
    <unused60>
    0.43
    <unused63>
    0.42
     ```
    0.41
    <0x0D>
    0.41
    inspection
    0.41
     Friday
    0.41
    POSITIVE LOGITS
     delito
    0.48
    愷
    0.46
     cuantit
    0.45
     offrire
    0.45
    猊
    0.45
    фы
    0.43
     Verhältnis
    0.43
     gamble
    0.43
     ничек
    0.42
    繧
    0.42
    Activations Density 0.000%

    No Known Activations