© 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. 90863
    Prev
    Next
    INDEX
    Explanations

    understanding and interpretation of knowledge

    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
    are
    0.54
    i
    0.49
    names
    0.47
    elles
    0.46
    ी
    0.45
    across
    0.41
    orge
    0.41
    nam
    0.40
    nales
    0.40
    ke
    0.40
    POSITIVE LOGITS
     useless
    0.52
     firmware
    0.51
    𒊬
    0.49
     firmness
    0.49
     নেই
    0.48
    が増
    0.48
     funziona
    0.47
     suporte
    0.47
     nici
    0.47
    𒊓
    0.47
    Activations Density 0.006%

    No Known Activations