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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 23947
    Prev
    Next
    INDEX
    Explanations

    narrative content generation

    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_40_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
     pensiero
    0.46
    踉
    0.44
    𒋾
    0.44
    枓
    0.43
     pensamiento
    0.43
     tangente
    0.42
     pensamento
    0.42
    amending
    0.41
    mfrac
    0.41
    $\--
    0.40
    POSITIVE LOGITS
    Narr
    0.51
     narr
    0.50
    narr
    0.47
     narration
    0.45
     narrative
    0.42
     Narr
    0.41
     deactivate
    0.41
     }
    0.40
    ;
    0.39
     (
    0.39
    Activations Density 0.000%

    No Known Activations