© 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. 8957
    Prev
    Next
    INDEX
    Explanations

    evoke feeling or meaning

    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
     keychain
    0.46
     rougeâtres
    0.46
    criminals
    0.46
     iniziamo
    0.45
     scammers
    0.44
     hoodies
    0.43
    椛
    0.42
     veggies
    0.41
     shenanigans
    0.41
     chuckled
    0.41
    POSITIVE LOGITS
     rhythms
    0.50
     rhythm
    0.49
     trans
    0.49
    积
    0.46
     rhythmic
    0.45
     poet
    0.45
     sensibility
    0.45
     evocative
    0.44
     raconte
    0.44
    Trans
    0.43
    Activations Density 0.142%

    No Known Activations