© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138370
    Prev
    Next
    INDEX
    Explanations

    including device, for variations, that deeper

    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
     Requested
    0.47
     sentado
    0.46
    மைச்சர்
    0.45
    ché
    0.44
    寬
    0.44
    ací
    0.44
    liği
    0.43
     requerido
    0.43
    मोदी
    0.42
     grupy
    0.42
    POSITIVE LOGITS
    s
    0.45
    gdx
    0.44
     обознача
    0.41
     if
    0.40
     ইং
    0.40
     आकांक्षा
    0.40
     hoping
    0.39
     forceful
    0.39
     ски
    0.39
    certain
    0.39
    Activations Density 0.002%

    No Known Activations