© 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. 15-GEMMASCOPE-2-RES-262K
    7. 69789
    Prev
    Next
    INDEX
    Explanations

    solutions for everyone

    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_15_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
     botched
    1.60
    cesis
    1.55
     outsourced
    1.55
    azeera
    1.55
    ออกจาก
    1.53
     antigu
    1.50
     Ubuy
    1.50
    ₤
    1.49
    honia
    1.49
     ioutil
    1.48
    POSITIVE LOGITS
    SM
    1.43
    Ign
    1.38
    resol
    1.36
    fl
    1.33
     résolution
    1.33
    ver
    1.32
     Rés
    1.31
    pp
    1.31
     ign
    1.30
     Veranst
    1.29
    Activations Density 0.001%

    No Known Activations