© 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. 14213
    Prev
    Next
    INDEX
    Explanations

    certain guideline

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

    statements about future events

    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
    स्टोन
    0.51
    wchar
    0.48
    ᱔
    0.46
    ፦
    0.46
    angat
    0.45
     بواسطة
    0.44
     welchen
    0.44
     Schae
    0.44
     ಬಳಕೆ
    0.42
    শিদ
    0.41
    POSITIVE LOGITS
    "。
    0.47
    цна
    0.46
     termina
    0.46
     fixa
    0.46
    뺑
    0.44
     syring
    0.44
    承
    0.43
     grasses
    0.42
    白
    0.42
    白的
    0.41
    Activations Density 0.000%

    No Known Activations