© 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. 54033
    Prev
    Next
    INDEX
    Explanations

    love, completion, quality, insurance

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

    fashion and accessories

    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
    ঁর
    0.48
     ',');
    0.44
     regretted
    0.43
    bor
    0.42
    furt
    0.42
     juniors
    0.42
    하십시오
    0.42
     regrets
    0.41
     Memoirs
    0.41
     journal
    0.40
    POSITIVE LOGITS
    供应链
    0.49
    𝚆
    0.47
    精准
    0.47
    فيف
    0.46
    侬
    0.46
     сила
    0.45
    业内
    0.45
    粒
    0.45
    ρηση
    0.45
    刮
    0.45
    Activations Density 0.000%

    No Known Activations