© 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-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 113412
    Prev
    Next
    INDEX
    Explanations

    may not

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

    maximum of minimums to minimum of maximums

    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
    Adresse
    0.45
    mest
    0.45
     estar
    0.44
    ↵↵↵↵
    0.43
     deliverance
    0.43
     praxis
    0.42
    Straße
    0.41
    ↵↵↵↵↵
    0.41
     warmest
    0.41
    ISC
    0.41
    POSITIVE LOGITS
    使う
    0.46
     ترکیب
    0.45
    निटी
    0.42
     Defined
    0.42
     توسیع
    0.42
    વાહી
    0.42
    াবার
    0.42
    धुनिक
    0.41
    ently
    0.41
     درمیان
    0.41
    Activations Density 0.000%

    No Known Activations