© 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-65K
    7. 4482
    Prev
    Next
    INDEX
    Explanations

    speech, numbers, and facts

    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
    ophores
    0.61
    زر
    0.60
     "</
    0.60
     sœurs
    0.57
     fenô
    0.53
    ustering
    0.52
     frères
    0.51
    rete
    0.50
    Meri
    0.50
    inizin
    0.49
    POSITIVE LOGITS
    ++
    1.77
     Classical
    1.65
     Draft
    1.65
     Angus
    1.64
     British
    1.64
     LIN
    1.63
     Blitz
    1.63
     Catholic
    1.62
     Italian
    1.62
     AIR
    1.61
    Activations Density 0.036%

    No Known Activations