© 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. 100839
    Prev
    Next
    INDEX
    Explanations

    states of specific things

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

    instructional sentences

    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
    ANDO
    0.51
     द्वारा
    0.45
     દ્વારા
    0.45
     ರಿಂದ
    0.45
    annen
    0.44
    UTR
    0.44
     ಉತ್
    0.44
    ➩
    0.44
    ospin
    0.43
    Laz
    0.43
    POSITIVE LOGITS
    tips
    0.53
    t
    0.50
     mexican
    0.47
     propuesta
    0.47
    j
    0.45
     în
    0.45
    
    0.45
    li
    0.44
    walls
    0.44
     russ
    0.44
    Activations Density 0.000%

    No Known Activations