© 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. 143803
    Prev
    Next
    INDEX
    Explanations

    Different types

    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
     cylindrical
    0.42
    ರುವುದರಿಂದ
    0.41
     crow
    0.40
     ciphertext
    0.40
     superfluous
    0.40
     ყ
    0.39
     urch
    0.39
    コマンド
    0.39
     本当
    0.39
     theft
    0.39
    POSITIVE LOGITS
    ?—
    0.44
     různ
    0.44
    Hungary
    0.43
    Gin
    0.43
    Gil
    0.43
    lipstick
    0.42
    Basel
    0.41
    Jazz
    0.41
    ﹙
    0.41
    Death
    0.41
    Activations Density 0.005%

    No Known Activations