© 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. 170038
    Prev
    Next
    INDEX
    Explanations

    evaluation, clinical, gradient

    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
    𝘂
    0.48
    us
    0.45
    voll
    0.44
    leta
    0.44
    𝗇
    0.43
    므로
    0.43
    nika
    0.43
    ਤਰ
    0.42
    承
    0.42
    inputs
    0.41
    POSITIVE LOGITS
     दहशत
    0.50
    几乎
    0.47
     Rheumat
    0.45
     neurolog
    0.44
     Downloads
    0.43
     Discipline
    0.42
     Bad
    0.41
     altamente
    0.40
     kötü
    0.40
     आतंक
    0.39
    Activations Density 0.010%

    No Known Activations