© 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. 106631
    Prev
    Next
    INDEX
    Explanations

    melt butter

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

    melting liquid or solid

    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
    indrical
    0.54
     endemic
    0.44
     infiltrating
    0.44
     affirmation
    0.43
    ле
    0.42
     elektr
    0.42
    q
    0.42
    aties
    0.42
     doctrines
    0.41
    ylmethyl
    0.40
    POSITIVE LOGITS
     melts
    0.66
     melted
    0.63
    MEL
    0.61
    Mel
    0.60
     melons
    0.59
     melting
    0.57
     Melting
    0.57
     melt
    0.57
     mel
    0.55
    熔
    0.54
    Activations Density 0.086%

    No Known Activations