© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 55626
    Prev
    Next
    INDEX
    Explanations

    book volumes or docker volumes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    imbo
    0.45
    ifte
    0.44
    ANGAN
    0.41
    adhar
    0.38
     Hallmark
    0.38
    anze
    0.37
    angered
    0.37
    獠
    0.37
    ahoo
    0.37
    Leaf
    0.37
    POSITIVE LOGITS
     volume
    1.70
     Volume
    1.68
    Volume
    1.63
     volumes
    1.58
    volume
    1.48
     Volumes
    1.47
     volumen
    1.39
    Volumes
    1.38
    VOLUME
    1.35
     VOLUME
    1.34
    Activations Density 0.026%

    No Known Activations