© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 84016
    Prev
    Next
    INDEX
    Explanations

    cryptography and ciphers

    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
     Montgomery
    0.48
    acom
    0.48
     également
    0.46
     Lee
    0.45
     Lyons
    0.44
    砰
    0.44
     tellement
    0.43
    ker
    0.42
    otta
    0.42
    ή
    0.42
    POSITIVE LOGITS
    urchase
    0.49
    SECOND
    0.48
     renewals
    0.48
    currency
    0.46
     thefts
    0.45
    expensive
    0.45
     구매
    0.45
    િ
    0.45
    CIRCLE
    0.44
    饌
    0.44
    Activations Density 0.010%

    No Known Activations