© 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. 23934
    Prev
    Next
    INDEX
    Explanations

    instructions and procedures

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

    quarter note

    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
    СТ
    0.47
     पुत्र
    0.45
     сын
    0.44
     дочь
    0.43
    嗤
    0.42
    ipynb
    0.40
    }}=
    0.39
    從小
    0.39
    }[\
    0.39
    }\|
    0.39
    POSITIVE LOGITS
    -,
    0.39
    的设计
    0.38
     ország
    0.38
     barbers
    0.37
     barber
    0.36
    zentrum
    0.36
     cabaret
    0.34
    ScrollView
    0.34
     allé
    0.34
     Certificate
    0.33
    Activations Density 0.001%

    No Known Activations