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

    Neuronpedia

    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. 239
    Prev
    Next
    INDEX
    Explanations

    questions about specifics

    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
    rinsic
    3.38
    煖
    3.00
    7
    2.99
     nasc
    2.84
    quetas
    2.82
    5
    2.81
    8
    2.79
    getExternal
    2.77
    }°
    2.77
    6
    2.75
    POSITIVE LOGITS
     ann
    2.72
     organisers
    2.70
     arrows
    2.64
     nets
    2.62
     reveals
    2.59
     estimates
    2.53
     one
    2.50
    planned
    2.48
     fixes
    2.48
     tide
    2.48
    Activations Density 0.000%

    No Known Activations