© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 50868
    Prev
    Next
    INDEX
    Explanations

    content types: text, audio, code

    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
    ABASE
    0.50
    EXTENSION
    0.46
    ModelAttribute
    0.46
    카
    0.46
    𝙰
    0.46
    Lx
    0.45
    TEGER
    0.45
    ijama
    0.45
    LAYOUT
    0.44
    জ
    0.44
    POSITIVE LOGITS
     Trade
    0.48
     topology
    0.47
    ளுக்கான
    0.46
     trade
    0.45
     doomed
    0.45
     land
    0.45
     Kiss
    0.44
     něm
    0.44
     hockey
    0.43
     vortex
    0.43
    Activations Density 0.002%

    No Known Activations