© 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. 25602
    Prev
    Next
    INDEX
    Explanations

    The other, en masse, states

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

    deliberately drab, trying to

    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
     argumentation
    0.50
     amplitudes
    0.47
    t
    0.46
     intensities
    0.44
     sacram
    0.44
     analyse
    0.43
     identific
    0.43
     alarg
    0.43
     inequities
    0.42
    ig
    0.42
    POSITIVE LOGITS
    ებული
    0.47
    ⦿
    0.44
    ტრ
    0.44
     Injury
    0.44
    ☠
    0.43
    ǚ
    0.42
     Wharton
    0.42
     ग्रेड
    0.42
     던
    0.41
    買った
    0.41
    Activations Density 0.000%

    No Known Activations