© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1571
    Prev
    Next
    INDEX
    Explanations

    multi-lingual code and text snippets

    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_16k_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
    ~$
    1.63
     elementary
    1.59
     surprisingly
    1.57
     fundamental
    1.53
     Ira
    1.52
    terror
    1.48
    ā
    1.48
    🍭
    1.48
     Oklahoma
    1.48
     autopilot
    1.48
    POSITIVE LOGITS
    cimento
    1.23
     مشرف
    1.20
     смогли
    1.20
    тения
    1.19
    رفع
    1.19
    iativa
    1.16
     deportiva
    1.13
     سیر
    1.13
    ặn
    1.12
    itag
    1.11
    Activations Density 0.032%

    No Known Activations