© 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. 88
    Prev
    Next
    INDEX
    Explanations

    There's no single

    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
     sabbam
    0.28
    㞖
    0.26
    😟
    0.26
    ისუფ
    0.25
     木
    0.25
     cinder
    0.25
     =(
    0.24
     carcinoma
    0.24
     Coroner
    0.24
     CGRect
    0.24
    POSITIVE LOGITS
    s
    0.32
    на
    0.28
    сев
    0.27
    q
    0.26
     varias
    0.26
    те
    0.24
    uge
    0.24
    clave
    0.24
    ли
    0.23
    e
    0.23
    Activations Density 0.051%

    No Known Activations