© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202749
    Prev
    Next
    INDEX
    Explanations

    deliberately threatening or given limited

    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
    subnet
    0.47
     οπο
    0.46
    leased
    0.44
     ὁ
    0.44
     било
    0.43
     الْم
    0.41
     Аб
    0.40
     thereon
    0.40
    允許
    0.39
    ueness
    0.39
    POSITIVE LOGITS
    ی
    0.56
    نی
    0.49
    ностей
    0.46
     favourites
    0.46
    鸟
    0.46
    pector
    0.45
    тивно
    0.44
     noisy
    0.43
     storm
    0.43
     Boogie
    0.43
    Activations Density 0.005%

    No Known Activations