© 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. 95612
    Prev
    Next
    INDEX
    Explanations

    easy

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

    account creation and remote

    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
    ೇಶ
    0.41
    outlined
    0.40
    vej
    0.39
    ↵↵
    0.39
    avaju
    0.39
    也不是
    0.38
     هذا
    0.38
    ensibly
    0.38
    の上に
    0.38
     potranno
    0.38
    POSITIVE LOGITS
    Bacteria
    0.49
    Checksum
    0.47
     meraih
    0.46
    󠁧
    0.45
    кает
    0.45
     Corrections
    0.45
    Implementing
    0.44
    Rit
    0.44
     продви
    0.43
    Lift
    0.43
    Activations Density 0.000%

    No Known Activations