© 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. 121556
    Prev
    Next
    INDEX
    Explanations

    invited female students

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

    technological, philosophy, culture, inclusive

    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
    raw
    0.49
    在
    0.48
     in
    0.46
     reprezent
    0.46
     kil
    0.45
     kilom
    0.45
    GD
    0.44
    :#
    0.43
    JP
    0.43
    land
    0.41
    POSITIVE LOGITS
     அவன்
    0.49
    晎
    0.48
     वेलकम
    0.46
     చేసిన
    0.46
    㥉
    0.45
    abhavo
    0.45
     hastened
    0.45
    씐
    0.44
     Turismo
    0.44
     нуля
    0.44
    Activations Density 0.002%

    No Known Activations