© 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. 142024
    Prev
    Next
    INDEX
    Explanations

    color , type

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

    Spelling errors, portfolio, scenes, negate

    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
    s
    0.58
    7
    0.58
    1
    0.55
    9
    0.52
    emp
    0.50
    x
    0.50
    5
    0.50
    y
    0.50
    8
    0.50
    any
    0.49
    POSITIVE LOGITS
     máquinas
    0.54
     actuales
    0.54
     radicales
    0.54
     ល
    0.53
     montagnes
    0.52
     লিখিতে
    0.52
     criaturas
    0.52
     edificios
    0.51
     ordnance
    0.50
    ᇁ
    0.50
    Activations Density 0.000%

    No Known Activations