© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78570
    Prev
    Next
    INDEX
    Explanations

    conditions and requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incroy
    0.49
    <0x0D>
    0.48
     MNIST
    0.45
    すぐに
    0.42
     incredible
    0.42
    立即
    0.41
     Texture
    0.41
     Cartoon
    0.40
     upcoming
    0.40
     advice
    0.40
    POSITIVE LOGITS
    𒊭
    0.46
     rispetto
    0.45
     sämt
    0.45
     وغ
    0.44
    衹
    0.44
    esehen
    0.43
    za
    0.43
     allein
    0.43
    furnished
    0.43
    praw
    0.43
    Activations Density 0.002%

    No Known Activations