© 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. 16-GEMMASCOPE-2-RES-262K
    7. 19944
    Prev
    Next
    INDEX
    Explanations

    shooting practice and targets

    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_16_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
     vän
    0.58
     to
    0.57
    4
    0.57
     A
    0.55
     H
    0.52
    _
    0.52
     pria
    0.52
     mannen
    0.51
     d
    0.51
     mRNA
    0.50
    POSITIVE LOGITS
    idcoin
    0.63
    }$\
    0.55
    第壹百
    0.53
    𝙧
    0.52
    נה
    0.52
     Ć
    0.50
    Ŷ
    0.50
     अभ्यास
    0.49
    தீ
    0.49
    𝙊
    0.49
    Activations Density 0.010%

    No Known Activations