© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 47326
    Prev
    Next
    INDEX
    Explanations

    initial, direct, immediately

    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_65k_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
    และ
    0.47
    ा
    0.46
    妛
    0.46
    垃
    0.46
    及
    0.46
    㐫
    0.45
    和
    0.44
    以及
    0.44
    ছোট
    0.44
    ござい
    0.43
    POSITIVE LOGITS
     보니
    0.42
     predicament
    0.41
     Baptism
    0.41
     (=
    0.40
     disagreement
    0.40
     arguments
    0.40
     wären
    0.40
     platelets
    0.39
     Arguments
    0.38
     vassals
    0.38
    Activations Density 0.003%

    No Known Activations