© 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. 4467
    Prev
    Next
    INDEX
    Explanations

    bug or FileNotFoundError

    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
    afa
    2.25
     작동
    2.20
     nihil
    2.16
     Paly
    2.16
    ificacion
    2.15
    funcion
    2.15
     funzionamento
    2.14
    氦
    2.14
     Funcion
    2.14
     Substances
    2.12
    POSITIVE LOGITS
    segment
    1.32
    Segment
    1.13
     segment
    1.12
     Segment
    1.09
    SEG
    0.87
     segmental
    0.85
     segmentation
    0.85
     of
    0.81
     is
    0.78
     delivers
    0.76
    Activations Density 0.021%

    No Known Activations