© 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. 245923
    Prev
    Next
    INDEX
    Explanations

    permission game of variety

    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
     on
    0.47
    s
    0.47
     annot
    0.45
     камер
    0.45
     оцени
    0.44
    rand
    0.44
    on
    0.42
    rates
    0.41
    }}}
    0.40
    slots
    0.40
    POSITIVE LOGITS
    OKR
    0.51
    銀
    0.49
     করবার
    0.49
    饌
    0.49
     করিয়াছেন
    0.48
    சிரிய
    0.48
     divina
    0.48
     srebr
    0.48
     घंट
    0.47
    燦
    0.47
    Activations Density 0.001%

    No Known Activations