© 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. 113058
    Prev
    Next
    INDEX
    Explanations

    object selections

    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
     Ansch
    0.46
     TAG
    0.45
     Predicted
    0.45
     $$$
    0.45
     Wochenende
    0.45
     libri
    0.44
     belanja
    0.44
    gettags
    0.44
     Karachi
    0.43
     pratis
    0.43
    POSITIVE LOGITS
    с
    0.55
    nonce
    0.51
    س
    0.51
    ס
    0.51
    dis
    0.50
    S
    0.49
    first
    0.47
    են
    0.47
    cons
    0.47
    դ
    0.47
    Activations Density 0.001%

    No Known Activations