© 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. 390
    Prev
    Next
    INDEX
    Explanations

    labor, loves younger

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     yöntem
    1.89
     methodologies
    1.81
     yönt
    1.81
     méthodes
    1.81
    囝
    1.80
    éristique
    1.72
    Method
    1.71
    ungannya
    1.69
     schemes
    1.68
     evidences
    1.68
    POSITIVE LOGITS
     at
    1.54
    Diffuse
    1.46
    rinsic
    1.43
     etter
    1.38
    latent
    1.36
    8
    1.35
    ATTR
    1.25
    тип
    1.25
     efter
    1.22
    raw
    1.21
    Activations Density 0.110%

    No Known Activations