© 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
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 31582
    Prev
    Next
    INDEX
    Explanations

    & RAM, like you

    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
    on
    0.60
     случа
    0.58
     on
    0.55
    lar
    0.48
    ser
    0.45
    les
    0.45
    arf
    0.45
    一
    0.45
    profil
    0.43
    hos
    0.43
    POSITIVE LOGITS
    іо
    0.50
    間で
    0.46
    শিশু
    0.44
    ひとり
    0.44
    ୌ
    0.44
    簱
    0.44
     گلوکار
    0.44
    ラクマ
    0.43
     సినిమాలో
    0.43
    ɴ
    0.43
    Activations Density 0.000%

    No Known Activations