© 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. 31-GEMMASCOPE-2-RES-262K
    4. 41235
    Prev
    Next
    INDEX
    Explanations

    light illuminating dust motes

    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
     określ
    0.47
     arco
    0.43
    广泛
    0.41
    续
    0.40
     trigo
    0.39
     scriv
    0.39
    存在する
    0.39
    线上
    0.38
     apnea
    0.38
     subscribe
    0.37
    POSITIVE LOGITS
    esehatan
    0.52
    ఈ
    0.49
    ným
    0.46
    nehmen
    0.46
    resher
    0.45
     состоялась
    0.45
    unternehmen
    0.44
    EVERY
    0.44
    res
    0.43
    ystems
    0.43
    Activations Density 0.011%

    No Known Activations