© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 275
    Prev
    Next
    INDEX
    Explanations

    audio engineering voice

    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
    ertel
    1.54
     bibliography
    1.50
     selectors
    1.47
    }}=-\
    1.46
    sbom
    1.45
     nombreux
    1.43
    ydent
    1.41
    sgál
    1.41
     itinerary
    1.40
    속
    1.39
    POSITIVE LOGITS
     примерно
    2.61
    resonant
    2.47
    rier
    2.44
    یک
    2.40
    land
    2.30
    کرد
    2.29
    عی
    2.27
    riere
    2.27
    riers
    2.26
     declaratory
    2.25
    Activations Density 0.281%

    No Known Activations