© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2145
    Prev
    Next
    INDEX
    Explanations

    writing stories

    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_65k_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
    ↵↵
    0.55
    The
    0.48
    on
    0.46
    rials
    0.46
    rias
    0.44
    ت
    0.44
    hets
    0.44
    0.43
    ñ
    0.43
    ش
    0.42
    POSITIVE LOGITS
     alcuni
    0.62
     przen
    0.62
     STORY
    0.62
     ovvero
    0.61
     amulet
    0.59
     apie
    0.59
     racconto
    0.59
     aprire
    0.59
     histoires
    0.58
     REGIUNI
    0.58
    Activations Density 0.432%

    No Known Activations