© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 111644
    Prev
    Next
    INDEX
    Explanations

    visiting here or page

    np_acts-logits-general · gemini-2.5-flash-lite

    Handling rules, research, RL, mastering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )\}
    0.44
     KFC
    0.42
     *)$
    0.42
    ிகள்
    0.41
    み
    0.41
     microphone
    0.40
     franch
    0.40
    riu
    0.40
     impairments
    0.40
    ulants
    0.40
    POSITIVE LOGITS
    获奖
    0.48
    }=[
    0.45
    avid
    0.45
    }^{*}=\
    0.44
     ridd
    0.44
    loj
    0.43
    Economy
    0.43
     निकलता
    0.42
    jaty
    0.42
    컬
    0.41
    Activations Density 0.000%

    No Known Activations