© 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. 18173
    Prev
    Next
    INDEX
    Explanations

    literary and historical analysis

    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
    you
    0.40
     you
    0.39
    N
    0.37
     your
    0.35
    your
    0.35
     optionally
    0.35
    if
    0.33
    または
    0.33
    Y
    0.32
     আপনি
    0.32
    POSITIVE LOGITS
     traged
    0.35
     satir
    0.33
     absur
    0.32
     postwar
    0.32
     influential
    0.31
     époque
    0.31
     modernist
    0.31
     disillusioned
    0.31
     populist
    0.30
     misog
    0.30
    Activations Density 0.001%

    No Known Activations