© 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-65K
    4. 5038
    Prev
    Next
    INDEX
    Explanations

    listing items and classifications

    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
     xa
    0.55
    ilung
    0.48
     ㅛ
    0.47
     node
    0.47
    urist
    0.46
     रोकथाम
    0.45
    ur
    0.45
     union
    0.45
     HSM
    0.45
     plugin
    0.45
    POSITIVE LOGITS
    មិន
    0.40
    ญ
    0.39
     remporte
    0.39
    득
    0.39
     απο
    0.38
    Writing
    0.38
    стной
    0.38
    जफ्फर
    0.38
     endoplasmic
    0.38
    жде
    0.38
    Activations Density 0.010%

    No Known Activations