© 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. 205297
    Prev
    Next
    INDEX
    Explanations

    born knowing, trusted brand, sometimes light

    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
    课
    0.52
    ъек
    0.48
     уров
    0.47
    вани
    0.45
    ре
    0.43
     ఆహ
    0.43
    количество
    0.43
     Dosage
    0.42
     wetter
    0.42
     Shabbat
    0.41
    POSITIVE LOGITS
    .
    0.58
    mile
    0.53
    esso
    0.49
    ene
    0.48
    embro
    0.47
    ⵙ
    0.47
    ian
    0.46
    eli
    0.46
    ão
    0.46
    test
    0.45
    Activations Density 0.003%

    No Known Activations