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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 120264
    Prev
    Next
    INDEX
    Explanations

    Elsa and concerned

    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_16_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
    </b>
    0.72
     geograf
    0.68
     squadre
    0.65
     equipes
    0.65
     apre
    0.64
     mempunyai
    0.64
     indiquant
    0.63
     αυτή
    0.63
     orient
    0.61
     sélectionnez
    0.61
    POSITIVE LOGITS
    。
    0.77
    ت
    0.76
    ed
    0.71
    _
    0.71
    <0x93>
    0.69
    лу
    0.68
    يد
    0.67
    лист
    0.66
     with
    0.65
     for
    0.64
    Activations Density 0.001%

    No Known Activations