© 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. 28540
    Prev
    Next
    INDEX
    Explanations

    Very Black

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

    multiply, destroy, remember, languages

    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
    atorial
    0.53
    仟
    0.47
    姆
    0.46
    acid
    0.46
     real
    0.44
    অল
    0.43
    酸
    0.42
    ார்
    0.42
    istic
    0.42
    })$.
    0.41
    POSITIVE LOGITS
     مما
    0.47
     লিখে
    0.46
    骖
    0.46
     سمت
    0.45
     LDGs
    0.45
    getVisibility
    0.44
     Mast
    0.44
     مؤثر
    0.43
     اض
    0.43
     számos
    0.43
    Activations Density 0.000%

    No Known Activations