© 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. 169000
    Prev
    Next
    INDEX
    Explanations

    debugging, deployment, and assessment

    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
    싶
    0.46
     tars
    0.43
     ریز
    0.43
    悗
    0.42
     вибра
    0.42
    विदा
    0.41
    ղ
    0.41
    찮
    0.41
    厕
    0.41
     поперед
    0.41
    POSITIVE LOGITS
     pyridine
    0.51
     aryl
    0.48
     Aroma
    0.47
    party
    0.47
     hydrophilic
    0.47
     advanced
    0.47
     diphenyl
    0.46
     mezcla
    0.44
     Jit
    0.43
     food
    0.43
    Activations Density 0.001%

    No Known Activations