© 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. 163226
    Prev
    Next
    INDEX
    Explanations

    service comparison

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

    organic molecules, acknowledge, ultimately leaning

    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
     importanti
    0.54
    ح
    0.52
     Player
    0.52
     grandi
    0.51
    da
    0.50
    bling
    0.50
    al
    0.50
     creando
    0.47
     sneaky
    0.47
     ena
    0.46
    POSITIVE LOGITS
    Ỡ
    0.49
    suited
    0.47
    IService
    0.46
    retry
    0.46
    ΙΑ
    0.45
    ]=='
    0.43
    LLAR
    0.43
    IZA
    0.42
    NaBr
    0.42
    及ひ
    0.42
    Activations Density 0.001%

    No Known Activations