© 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. 4747
    Prev
    Next
    INDEX
    Explanations

    language or cost reduction

    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
     Michel
    1.15
     INDIC
    1.11
    aign
    1.11
    aval
    1.03
    識
    1.03
     Sciences
    1.03
    versammlung
    1.02
    рави
    1.02
    什么样的
    0.99
    ̸
    0.98
    POSITIVE LOGITS
     costos
    1.69
     costi
    1.64
     rispar
    1.61
    减少
    1.60
     eficiencia
    1.57
     wasteful
    1.56
     coûts
    1.56
     ridurre
    1.53
    节省
    1.50
     tedious
    1.50
    Activations Density 0.328%

    No Known Activations