© 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. 203841
    Prev
    Next
    INDEX
    Explanations

    another a

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

    concepts like reduction, data, resources

    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
     LICENSE
    0.46
     treks
    0.45
    BigAutoField
    0.43
    ene
    0.42
     actions
    0.41
     /
    0.41
    Sunset
    0.40
    License
    0.40
     notes
    0.39
    PCR
    0.39
    POSITIVE LOGITS
    ק
    0.50
     recouvert
    0.50
    는
    0.50
     rzeczyw
    0.49
    洧
    0.49
    躲
    0.48
     Même
    0.47
    殒
    0.46
    בו
    0.46
     actuel
    0.46
    Activations Density 0.000%

    No Known Activations