© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68177
    Prev
    Next
    INDEX
    Explanations

    multi band

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ;//
    -1.01
    ḥ
    -0.94
    \#\#
    -0.90
     fácil
    -0.90
     GTX
    -0.90
     klasa
    -0.89
    ＝
    -0.87
    azzjoni
    -0.86
    ationen
    -0.86
     desaparición
    -0.85
    POSITIVE LOGITS
     ouvido
    1.06
     its
    0.97
    files
    0.96
    铤
    0.95
    shortcut
    0.93
     frischen
    0.93
     weißen
    0.91
    erom
    0.90
    了好
    0.88
    Atendimento
    0.87
    Activations Density 0.000%

    No Known Activations