© 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. 29761
    Prev
    Next
    INDEX
    Explanations

    may incorporate, May your, a ll

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

    spot instance

    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
     arrond
    0.50
     ?>
    0.48
    ⏭
    0.46
    prev
    0.45
    h
    0.45
     walkthrough
    0.45
    Charl
    0.44
    }></
    0.44
    ophe
    0.44
    preprocess
    0.44
    POSITIVE LOGITS
     Ï
    0.50
     Polk
    0.48
    ̀ng
    0.46
    ளி
    0.45
     Tập
    0.44
    ástica
    0.43
    斩
    0.43
     লাগিল
    0.42
     அவர்களுடைய
    0.42
    Ji
    0.41
    Activations Density 0.000%

    No Known Activations