© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 624
    Prev
    Next
    INDEX
    Explanations

    quotation marks followed by key terms

    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_16k_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
    y
    0.28
    ies
    0.27
     approximately
    0.26
    gly
    0.25
     significantly
    0.25
    }=
    0.24
     also
    0.24
    nel
    0.24
     from
    0.23
     även
    0.23
    POSITIVE LOGITS
    시대
    0.27
    <unused499>
    0.27
     měli
    0.27
    Թ
    0.25
    Ку
    0.25
    잊
    0.25
    до
    0.25
     کي
    0.24
    Ships
    0.24
    Perfect
    0.24
    Activations Density 1.079%

    No Known Activations