© 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. 6195
    Prev
    Next
    INDEX
    Explanations

    available / success / problems / cases / acre tract / engine similar / clarified comments

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

    specific nouns and activities

    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
     Elektrokhimiya
    0.23
     socalled
    0.23
     :=\
    0.21
    রত্ব
    0.20
    akkhati
    0.20
    জনকে
    0.19
    羮
    0.19
     ಪ್ರಯತ್ನ
    0.19
     আবদ্ধ
    0.19
     ذریع
    0.18
    POSITIVE LOGITS
    4
    0.38
    2
    0.29
    1
    0.29
    3
    0.29
    7
    0.29
    _
    0.28
    а
    0.28
    9
    0.28
    5
    0.28
    0
    0.27
    Activations Density 5.509%

    No Known Activations