© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79051
    Prev
    Next
    INDEX
    Explanations

    data-driven decision making

    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
    首都
    0.46
     Tät
    0.44
    ت
    0.43
    ברת
    0.42
     функций
    0.42
    ز
    0.41
     คูณ
    0.41
    猩
    0.41
    ྥ
    0.41
    䏹
    0.41
    POSITIVE LOGITS
     revoke
    0.55
     evacuate
    0.53
    ilo
    0.52
     inciner
    0.51
     fatal
    0.51
     Vodka
    0.51
     publicity
    0.49
     obstruct
    0.49
     harsher
    0.49
     October
    0.49
    Activations Density 0.001%

    No Known Activations