© 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. 169378
    Prev
    Next
    INDEX
    Explanations

    legal, requests, advice, praise

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

    hidden gem recommendations

    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
    ochromatic
    0.46
    oubtedly
    0.45
     cytochrome
    0.42
    izontal
    0.41
    ="/
    0.41
     undoubtedly
    0.40
    ceptors
    0.40
     ladders
    0.40
     rivers
    0.40
    ddagger
    0.40
    POSITIVE LOGITS
     opcoes
    0.47
     Oiseau
    0.47
    ைகளுக்கு
    0.46
     empleado
    0.46
     semilla
    0.46
    ০১
    0.45
     Antoni
    0.44
     immagine
    0.44
    葢
    0.44
     ময়
    0.43
    Activations Density 0.000%

    No Known Activations