© 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. 48323
    Prev
    Next
    INDEX
    Explanations

    versus, per, Awards, every, group, Inc

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

    affirmative statements

    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
    )
    0.46
     esemplari
    0.45
     Sure
    0.41
     Maybe
    0.41
    тал
    0.40
    ু
    0.40
     oración
    0.40
     Masses
    0.40
    ;
    0.40
    itipi
    0.40
    POSITIVE LOGITS
    CK
    0.48
     ቫ
    0.48
    निर्
    0.45
    yout
    0.44
    ುವುದ
    0.44
    moil
    0.44
    told
    0.44
    kd
    0.43
    に対し
    0.43
    addGroup
    0.43
    Activations Density 0.000%

    No Known Activations