© 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. 31-GEMMASCOPE-2-RES-262K
    7. 50878
    Prev
    Next
    INDEX
    Explanations

    isset($_

    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
    에
    0.47
    링
    0.46
    աբ
    0.46
    都不会
    0.46
    на
    0.45
    ለን
    0.43
    లో
    0.42
     перспек
    0.42
     simulates
    0.41
    하여
    0.41
    POSITIVE LOGITS
    溘
    0.45
    蕙
    0.44
     Wand
    0.43
     Themen
    0.42
     பேர்
    0.42
    pagina
    0.42
    Estoy
    0.42
     ibang
    0.41
     provenienti
    0.41
     Voices
    0.40
    Activations Density 0.001%

    No Known Activations