© 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. 195531
    Prev
    Next
    INDEX
    Explanations

    simplest approach

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

    your, an, dogs, why, future

    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
    锂
    0.53
    𝐴
    0.51
     загряз
    0.50
    是从
    0.49
    融入
    0.49
     jeho
    0.48
     NTIS
    0.48
     praticamente
    0.48
    র্মে
    0.48
    Sp
    0.48
    POSITIVE LOGITS
    ี
    0.54
    ially
    0.47
    䚯
    0.44
     diny
    0.43
    стіше
    0.42
    ህል
    0.42
    cez
    0.41
    мін
    0.41
    astan
    0.40
    チン
    0.40
    Activations Density 0.000%

    No Known Activations