© 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. 142162
    Prev
    Next
    INDEX
    Explanations

    vaginal intercourse

    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
    Trả
    0.57
    庀
    0.53
    гляда
    0.50
    Terrain
    0.49
    the
    0.48
     वातावरण
    0.48
    Noeud
    0.48
    '
    0.48
    𒌨
    0.48
    geke
    0.47
    POSITIVE LOGITS
     as
    0.71
     &
    0.54
     but
    0.54
     was
    0.52
     van
    0.52
    j
    0.52
     failed
    0.52
     des
    0.51
     dried
    0.51
     smiles
    0.51
    Activations Density 0.000%

    No Known Activations