© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126204
    Prev
    Next
    INDEX
    Explanations

    threat and tracking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    the
    0.53
    d
    0.52
    other
    0.47
    ://
    0.47
    m
    0.47
    dif
    0.46
    that
    0.46
    to
    0.45
    ("
    0.45
    The
    0.45
    POSITIVE LOGITS
     애
    0.54
     неделю
    0.53
    ፂ
    0.48
     აღმასრულ
    0.47
     ಏ
    0.47
     катего
    0.46
     каче
    0.45
     оператив
    0.44
     eko
    0.44
     заповед
    0.44
    Activations Density 0.002%

    No Known Activations