© 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. 110646
    Prev
    Next
    INDEX
    Explanations

    quality subsequent actions

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

    enjoyable because, could lead, risks revictimization

    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
     ၀
    0.43
     Hôtel
    0.43
     hotel
    0.42
     cohom
    0.42
     ১০০
    0.42
     régional
    0.42
     distributional
    0.41
     Dynkin
    0.41
     grande
    0.41
     hôtel
    0.41
    POSITIVE LOGITS
    ందని
    0.45
    앜
    0.45
    անում
    0.44
    icono
    0.43
    मॉर्निंग
    0.42
    कारात्मक
    0.41
     мая
    0.40
    երի
    0.40
     அவர்கள்
    0.40
     grun
    0.40
    Activations Density 0.012%

    No Known Activations