© 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. 27218
    Prev
    Next
    INDEX
    Explanations

    assigned, locked, permission

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

    who owns what

    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
    ček
    0.44
     الرياض
    0.41
     ตัด
    0.41
    🛡
    0.41
    ťa
    0.40
    চিত
    0.40
    čka
    0.40
     فروغ
    0.40
    ებმა
    0.39
    馕
    0.39
    POSITIVE LOGITS
     relevant
    0.52
     relevantes
    0.49
     بالنسب
    0.46
     alerted
    0.45
     alvo
    0.43
    Relevant
    0.43
    ListOf
    0.42
    otopic
    0.42
    酣
    0.42
     relevante
    0.42
    Activations Density 0.001%

    No Known Activations