© 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. 60731
    Prev
    Next
    INDEX
    Explanations

    negative or loss values

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

    negative calculations or values

    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
     tinggi
    0.47
    砻
    0.47
    vyš
    0.45
    pland
    0.42
     புது
    0.42
    cami
    0.41
     yüks
    0.41
    錡
    0.41
    hab
    0.41
     국민
    0.41
    POSITIVE LOGITS
     negative
    1.59
    Negative
    1.48
     Negative
    1.46
     negativo
    1.44
    negative
    1.42
     negatif
    1.41
     negativos
    1.36
     negativity
    1.34
     negat
    1.30
     negativ
    1.30
    Activations Density 0.016%

    No Known Activations