© 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. 3344
    Prev
    Next
    INDEX
    Explanations

    fiber optic

    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
    𒋻
    0.53
    𝘇
    0.52
    nętr
    0.51
    窣
    0.49
    Verlag
    0.48
     разом
    0.48
    𝘀
    0.48
    ẖ
    0.48
    雑誌
    0.48
     llega
    0.47
    POSITIVE LOGITS
    بار
    0.42
    ﺒ
    0.41
     cláus
    0.40
     geng
    0.40
     elk
    0.39
     prohibits
    0.38
    غيل
    0.37
    随着
    0.37
     وما
    0.36
    ajer
    0.35
    Activations Density 0.002%

    No Known Activations