© 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. 222414
    Prev
    Next
    INDEX
    Explanations

    MESSAGE PROMPT

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

    break down

    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
     विधायकों
    0.51
     रेपो
    0.49
    শের
    0.48
    Repos
    0.46
    蠟
    0.46
    عی
    0.45
     nghĩ
    0.45
    тись
    0.45
    ጒ
    0.45
    アップ
    0.44
    POSITIVE LOGITS
     for
    0.52
     chicks
    0.47
     arbitrage
    0.46
    lug
    0.46
    life
    0.44
     ecstasy
    0.44
     uncanny
    0.44
    z
    0.44
     imperialism
    0.44
     nationalism
    0.44
    Activations Density 0.003%

    No Known Activations