© 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. 3867
    Prev
    Next
    INDEX
    Explanations

    headings or labels

    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
    9
    0.87
    nilai
    0.86
     thermocou
    0.85
    8
    0.83
     escultura
    0.83
     emissivity
    0.77
    oprene
    0.76
    indeer
    0.75
    6
    0.73
     lorem
    0.73
    POSITIVE LOGITS
     Dig
    1.57
     Hilton
    1.55
    Hil
    1.55
     tangy
    1.54
     Kid
    1.54
     Hil
    1.51
     DOL
    1.49
     Mek
    1.49
     Davison
    1.49
     Sauce
    1.48
    Activations Density 0.019%

    No Known Activations