© 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. 31-GEMMASCOPE-2-RES-65K
    7. 6253
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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_31_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
     integro
    0.37
     غز
    0.37
    䁂
    0.36
    ালন
    0.36
    ikker
    0.35
    proses
    0.35
    aplik
    0.35
    cador
    0.34
    endeu
    0.34
    రికీ
    0.33
    POSITIVE LOGITS
     contra
    0.53
     underlining
    0.49
     *((
    0.42
     BYTE
    0.41
     push
    0.41
     Push
    0.41
     erasing
    0.40
     ch
    0.40
     Assay
    0.39
     lifelong
    0.39
    Activations Density 0.047%

    No Known Activations