© 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. 153568
    Prev
    Next
    INDEX
    Explanations

    month behind

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

    sentiment analysis

    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
    ature
    0.54
    air
    0.51
    U
    0.49
    high
    0.47
    led
    0.47
    N
    0.46
    inen
    0.46
    handling
    0.45
    haul
    0.45
    roll
    0.45
    POSITIVE LOGITS
    ígono
    0.53
     помочь
    0.52
    ❣️
    0.46
     thăm
    0.46
     aident
    0.46
     Lê
    0.45
     apreciar
    0.44
     invités
    0.44
     restar
    0.44
     lettera
    0.44
    Activations Density 0.000%

    No Known Activations