© 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. 40030
    Prev
    Next
    INDEX
    Explanations

    covering a lot of ground

    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
     dishon
    0.49
    鳕
    0.46
     Harriet
    0.46
     الطرف
    0.45
     disgraceful
    0.45
     prosa
    0.44
     Borden
    0.42
     były
    0.42
     तृ
    0.42
     Loyal
    0.42
    POSITIVE LOGITS
     scalability
    0.48
    ity
    0.47
    HD
    0.45
    int
    0.45
    (
    0.45
    ues
    0.44
    SS
    0.44
    zhou
    0.44
    MV
    0.43
    search
    0.42
    Activations Density 0.006%

    No Known Activations