© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3040
    Prev
    Next
    INDEX
    Explanations

    structural analysis, proximity, question

    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
     or
    1.75
     schemes
    1.34
    或其他
    1.32
    |
    1.31
     plans
    1.30
     timeline
    1.27
     proof
    1.27
     mechanism
    1.27
     scheme
    1.26
     |
    1.26
    POSITIVE LOGITS
     seulement
    2.52
     тільки
    1.99
     ainult
    1.98
    ificacion
    1.98
     yalnızca
    1.97
    ices
    1.95
     appena
    1.94
     mindre
    1.94
    анд
    1.93
     только
    1.91
    Activations Density 0.062%

    No Known Activations