© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1113
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     evidence
    1.72
     속
    1.69
    ților
    1.68
    gone
    1.65
    rück
    1.65
     on
    1.63
     voraus
    1.63
    evidence
    1.61
     suggesting
    1.61
    Proof
    1.60
    POSITIVE LOGITS
    ٧
    1.06
     biota
    1.05
    ().__
    1.04
     ауто
    0.98
    ٥
    0.98
    rinsic
    0.94
     len
    0.93
    ٦
    0.89
     plut
    0.88
     randint
    0.87
    Activations Density 2.853%

    No Known Activations