© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10264
    Prev
    Next
    INDEX
    Explanations

    explaining how

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

    the presence of the word “surviving” (i.e. mentions of survival) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_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
    OUR
    0.85
    Chord
    0.84
    Coco
    0.80
    Hector
    0.78
    L
    0.77
    Étienne
    0.77
    ų
    0.77
    θ
    0.76
    Floral
    0.75
    𝐀
    0.75
    POSITIVE LOGITS
     promulg
    0.88
     divulg
    0.87
     frantically
    0.86
     betterment
    0.85
     buyout
    0.85
     decisive
    0.82
     impatient
    0.82
     teleport
    0.82
     affirmatively
    0.82
     willful
    0.82
    Activations Density 0.000%

    No Known Activations