© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46370
    Prev
    Next
    INDEX
    Explanations

    descended likeinformal careitself downsister planet

    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_262k_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
    å
    0.50
    stellt
    0.47
    幸
    0.45
     perch
    0.42
     quid
    0.42
    忠
    0.42
     verantwort
    0.42
    Jonathan
    0.42
    永遠
    0.42
    Loy
    0.42
    POSITIVE LOGITS
     bitmaps
    0.55
     MTLTexture
    0.51
     Initialization
    0.49
     Primary
    0.48
     STEP
    0.48
     สามารถ
    0.47
     Scanning
    0.47
     Workshops
    0.47
     %,
    0.47
     প্যার
    0.47
    Activations Density 0.002%

    No Known Activations