© 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. 4877
    Prev
    Next
    INDEX
    Explanations

    text or code snippets

    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
     Вайлдберриз
    0.41
     épars
    0.40
    IDAY
    0.39
    ពិសេស
    0.39
     😂😂
    0.38
     ఉంటాయి
    0.37
     gonorrhea
    0.37
     القسمه
    0.37
     wodurch
    0.37
     kullanılır
    0.37
    POSITIVE LOGITS
    ↵
    0.37
     Maestro
    0.36
     ‘
    0.36
     Make
    0.33
     오랜
    0.33
    <0xE3>
    0.32
     homeland
    0.32
     The
    0.32
     S
    0.32
     seismic
    0.32
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.